Home » Publication » 19701

Dettaglio pubblicazione

2019, Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, Pages 1865-1867 (volume: 4)

Cooperative multi-agent deep reinforcement learning in soccer domains (04b Atto di convegno in volume)

CATACORA OCANA JIM MARTIN, Capobianco R., Riccio F., Nardi D.

In multi-robot reinforcement learning the goal is to enable a group of robots to learn coordinated behaviors from direct interaction with the environment. Here, we provide a comparison of two main approaches designed for tackling this challenge; namely, independent learners (IL) and joint-action learners (JAL). We evaluate these methods in a multi-robot cooperative and adversarial soccer scenario, called 2 versus 2 free-kick task, with simulated NAO humanoid robots as players. Our findings show that both approaches can achieve satisfying solutions, with JAL outperforming IL.
keywords
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma